Text Classification
Transformers
PyTorch
English
deberta-v2
reward-model
reward_model
RLHF
Inference Endpoints

A whole conversation instead of just the last query

#2
by fractalego - opened

Is it possible to include the whole prior conversation instead of the last query alone?
My understanding is that these training sets (and this model) don't allow it. Perhaps a future work could do this?

Sign up or log in to comment